1 citations · 3 across the 11 of their papers we have counts for
11 papers
Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
Vitória Barin Pacela, Vitória Barin-Pacela, Shruti Joshi +3
The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projecti…
Causality is Key for Interpretability Claims to Generalise
Shruti Joshi, Aaron Mueller, David Klindt +3
Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and…
FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios
Andrea Moleri, Christian Internò, Ali Raza +4
Federated Learning (FL) enables distributed optimization without compromising data sovereignty. Yet, where local label distributions are mutually exclusive, standard weight aggrega…
The Observer Effect in World Models: Invasive Adaptation Corrupts Latent Physics
Christian Internò, Jumpei Yamaguchi, Loren Amdahl-Culleton +3
Determining whether neural models internalize physical laws as world models, rather than exploiting statistical shortcuts, remains challenging, especially under out-of-distribution…
Superposition disentanglement of neural representations reveals hidden alignment
André Longon, David Klindt, Meenakshi Khosla
The superposition hypothesis states that single neurons may participate in representing multiple features in order for the neural network to represent more features than it has neu…
DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
Bryan Rodas, Natalie Montesino, Jakob Ambsdorf +2
Continued pretraining offers a promising solution for adapting foundation models to a new target domain. However, in specialized domains, available datasets are often very small, l…
AI-Generated Video Detection via Perceptual Straightening
Christian Internò, Robert Geirhos, Markus Olhofer +3
The rapid advancement of generative AI enables highly realistic synthetic videos, posing significant challenges for content authentication and raising urgent concerns about misuse.…
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
Patrik Reizinger, Randall Balestriero, David Klindt +1
Self-Supervised Learning (SSL) powers many current AI systems. As research interest and investment grow, the SSL design space continues to expand. The Platonic view of SSL, followi…
Cross-Entropy Is All You Need To Invert the Data Generating Process
Patrik Reizinger, Alice Bizeul, Attila Juhos +4
Supervised learning has become a cornerstone of modern machine learning, yet a comprehensive theory explaining its effectiveness remains elusive. Empirical phenomena, such as neura…
Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
Mark Ibrahim, David Klindt, Randall Balestriero
Deep Learning is often depicted as a trio of data-architecture-loss. Yet, recent Self Supervised Learning (SSL) solutions have introduced numerous additional design choices, e.g.,…
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Daniel Kunin, Allan Raventós, Clémentine Dominé +4
While the impressive performance of modern neural networks is often attributed to their capacity to efficiently extract task-relevant features from data, the mechanisms underlying…